Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add san-npm/skills-ws --skill crm-buildergit clone --depth 1 https://github.com/san-npm/skills-wsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/san-npm/skills-ws/crm-builder)<a href="https://agentmods.dev/skills/san-npm/skills-ws/crm-builder"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/crm-builder/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/san-npm/skills-ws/crm-builder"><img src="https://agentmods.dev/badge/skills/san-npm/skills-ws/crm-builder.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.05896 |
| Opus 5 | $0.00032 | $0.02948 |
| Sonnet 5 | $0.00013 | $0.01179 |
| Haiku 4.5 | $0.00006 | $0.00590 |
Grade A, and why
crm-builder scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 311 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CRM Builder
How to design a CRM that sales actually uses and that survives an audit — the data model, pipeline definitions, lifecycle logic, scoring, automation, and the privacy/compliance layer most "CRM checklists" skip.
This skill is the design/architecture layer. For platform-specific operational setup (building it inside HubSpot/Salesforce/Pipedrive admin), see the sibling crm-operations. For scoring models in depth see lead-scoring; for nurture/drip flows see email-sequence; for funnel stage strategy see sales-funnel; for forecasting and GTM metrics see revenue-operations. For EU specifics see eu-legal-compliance.
First principle: every field you add is a field a rep must fill, a column you must keep clean, and a piece of personal data you become legally responsible for. Model the minimum that drives a decision or an automation. Adoption dies from data-entry burden, not missing features.
1. Pipeline Design — Stages, Entry/Exit Criteria, SLA
A stage is only legitimate if it has an objective, verifiable entry criterion (not "rep feels good"). Vague stages produce garbage forecasts. Max 6–8 stages; more causes confusion and "parking" of deals.
Reference pipelines
B2B SaaS: Lead → MQL → SQL → Discovery → Demo → Proposal → Negotiation → Closed Won / Closed Lost
B2B Services: Inquiry → Qualified → Scoping Call → Proposal → Contract Out → Closed Won / Closed Lost
B2C / E-comm: Visitor → Lead → First Purchase → Repeat → VIP / Churned
PLG / Self-serve: Signup → Activated → Habit → Team Invite → Paid → Expansion
Stage definitions (B2B SaaS) — entry criterion, exit criterion, SLA
| Stage | Entry criterion (objective) | Exit criterion (to advance) | SLA / max age | Default win-prob |
|---|---|---|---|---|
| MQL | Hit marketing score threshold OR requested demo | Owner assigned + first touch logged | 1 business day to first touch | 5% |
| SQL | Rep confirmed ICP fit + a real problem (BANT/CHAMP qualified) | Discovery call booked | 3 days | 10% |
| Discovery | Discovery call held; pain + impact documented | Demo agenda agreed | 7 days | 20% |
| Demo | Tailored demo delivered to a decision influencer | Verbal interest + next step set | 7 days | 40% |
| Proposal | Pricing/scope sent in writing | Proposal acknowledged + reviewed | 10 days | 60% |
| Negotiation | Terms/redlines or procurement engaged | Verbal yes or signature path agreed | 14 days | 80% |
| Closed Won | Signed contract / payment | — | — | 100% |
| Closed Lost | Explicit no, or no response past SLA | Loss reason required | — | 0% |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 311 lines · 64 tokens per session scan A 806f1b8e958c
crm-builder is a skill published in the GitHub repository san-npm/skills-ws (2 stars, last pushed 3d ago), licensed MIT. It adds 64 tokens to every session and 5,896 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…